About
Welcome to my research profile. I focus on building inherently aligned, natively steerable systems attuned to dynamic human preferences.
Research Projects
Active Preference Alignment
A theoretically grounded, training-free alignment method based on Sequential Monte Carlo sampling and Feynman-Kac Correctors that integrates online preference signals directly into the latent generative process.
To be submitted to ICML 2026
Cross-Domain AI Semantic Recognition Framework
A context-aware embedding pipeline that transforms unstructured clinical narratives into structured, quantifiable behavioral ontologies. Treats clinical event extraction as a dense vector retrieval problem, establishing a scalable protocol for computational phenotyping.
Dynamic Cognition Lab, WashU | Supervised by Prof. Jeffrey M. Zacks